ReLViC: Loss-Resilient Learned Video Coding with Dispersed Packetization and Controllable Packet Dependencies
2026-08-31 • Multimedia
Multimedia
AI summaryⓘ
The authors developed ReLViC, a new method to improve video compression when some data packets are lost during transmission. Their system spreads important data across packets and uses a special Transformer model to both compress and recover missing pieces. They designed a way to balance between compression quality and error impact without needing to retrain the model. Through careful training and testing, the authors showed that ReLViC works better than existing methods when many packets are lost.
learned video codingpacket losslatent tokensTransformerentropy modelingforward error correctionReed-Solomontemporal predictioncompression efficiencyerror propagation
Authors
Xuyang Chen, Daquan Feng, Xianfu Chen, Xiang-Gen Xia
Abstract
Packet loss can severely impair learned video coding because missing latent tokens compromise both spatial reconstruction and temporal prediction. We present ReLViC, a loss-resilient learned video coding framework that jointly addresses latent coding and packet-loss recovery. ReLViC disperses spatially adjacent latent tokens across packets and employs a dual-purpose Transformer to estimate entropy-model parameters during coding and reconstruct missing latent tokens at the receiver. It controls packet dependencies through a periodic-reset packet-context topology parameterized by the segment length, thereby tuning the trade-off between compression efficiency and error-propagation range without retraining. A three-stage progressive training procedure establishes single-frame coding, learns temporal context for entropy modeling, and then optimizes the recovery of masked latent tokens under simulated packet loss. Experiments using burst-loss traces evaluate ReLViC against H.265 protected by Reed--Solomon forward error correction (FEC) and GRACE, a loss-resilient learned video codec. ReLViC delivers more stable reconstruction and outperforms both baselines under severe packet loss.